Set threshold resnet18 pytorch

from PIL import Image
import torch
from torchvision import transforms
input_image = Image.open("img/danbooru_resnet1.png") # load an image of your choice
preprocess = transforms.Compose([
    transforms.Resize(360),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.7137, 0.6628, 0.6519], std=[0.2970, 0.3017, 0.2979]),
])
input_tensor = preprocess(input_image)
input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model

if torch.cuda.is_available():
    input_batch = input_batch.to('cuda')
    model.to('cuda')

with torch.no_grad():
    output = model(input_batch)

# The output has unnormalized scores. To get probabilities, you can run a sigmoid on it.
probs = torch.sigmoid(output[0]) # Tensor of shape 6000, with confidence scores over Danbooru's top 6000 tags

# Second part of the code 
# to set a threshold value and to use it 
tmp = probs[probs > thresh]
inds = probs.argsort(descending=True)

Source: github.com

Similar codes

2 votes138 views2 answers
Return codecs.charmap_decode(input,self.errors,decoding_table)[0] UnicodeDecodeError: 'charmap' codec can't decode byte 0x8d in position 280: character maps to <undefined>
Python
0 vote166 views1 answer
Split into list into even chunks
Python
3 votes151 views2 answers
Draw bounding box on image python opencv
Python
12 votes143 views2 answers
Python string to hex
Python
0 vote146 views1 answer
How to convert data into numerical dataset
Python
0 vote152 views1 answer
Maximum count of replacements in python
Python
0 vote140 views1 answer
Shuffle the data before GridSearchCV
Python
-1 vote139 views2 answers
Format timedelta python
Python
2 votes147 views1 answer
Shutdown/restart/hibernate/logoff windows with python
Python
21 votes159 views6 answers
Last element of list python
Python